Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network
Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and cl...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/ddc17f8e630043b38ea52c5be6620884 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:ddc17f8e630043b38ea52c5be6620884 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:ddc17f8e630043b38ea52c5be66208842021-11-25T18:57:20ZBangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network10.3390/s212275451424-8220https://doaj.org/article/ddc17f8e630043b38ea52c5be66208842021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7545https://doaj.org/toc/1424-8220Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and classification of Bangladeshi native vehicle types. An extensive dataset of Bangladeshi native vehicles, encompassing 10,440 images, was developed. Here, the images are categorized into 13 common vehicle classes in Bangladesh. The method utilized was a residual network (ResNet-50)-based model, with extra classification blocks added to improve performance. Here, vehicle type features were automatically extracted and categorized. While conducting the analysis, a variety of metrics was used for the evaluation, including accuracy, precision, recall, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>F</mi><mn>1</mn></msub><mtext> </mtext><mo>−</mo><mtext> </mtext><mi mathvariant="italic">Score</mi></mrow></semantics></math></inline-formula>. In spite of the changing physical properties of the vehicles, the proposed model achieved progressive accuracy. Our proposed method surpasses the existing baseline method as well as two pre-trained DL approaches, AlexNet and VGG-16. Based on result comparisons, we have seen that, in the classification of Bangladeshi native vehicle types, our suggested ResNet-50 pre-trained model achieves an accuracy of 98.00%.Md Mahibul HasanZhijie WangMuhammad Ather Iqbal HussainKaniz FatimaMDPI AGarticlenative vehicle type classificationDeshi-BD vehicle datasetdeep learningtransfer learningResNet-50Chemical technologyTP1-1185ENSensors, Vol 21, Iss 7545, p 7545 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
native vehicle type classification Deshi-BD vehicle dataset deep learning transfer learning ResNet-50 Chemical technology TP1-1185 |
spellingShingle |
native vehicle type classification Deshi-BD vehicle dataset deep learning transfer learning ResNet-50 Chemical technology TP1-1185 Md Mahibul Hasan Zhijie Wang Muhammad Ather Iqbal Hussain Kaniz Fatima Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
description |
Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and classification of Bangladeshi native vehicle types. An extensive dataset of Bangladeshi native vehicles, encompassing 10,440 images, was developed. Here, the images are categorized into 13 common vehicle classes in Bangladesh. The method utilized was a residual network (ResNet-50)-based model, with extra classification blocks added to improve performance. Here, vehicle type features were automatically extracted and categorized. While conducting the analysis, a variety of metrics was used for the evaluation, including accuracy, precision, recall, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>F</mi><mn>1</mn></msub><mtext> </mtext><mo>−</mo><mtext> </mtext><mi mathvariant="italic">Score</mi></mrow></semantics></math></inline-formula>. In spite of the changing physical properties of the vehicles, the proposed model achieved progressive accuracy. Our proposed method surpasses the existing baseline method as well as two pre-trained DL approaches, AlexNet and VGG-16. Based on result comparisons, we have seen that, in the classification of Bangladeshi native vehicle types, our suggested ResNet-50 pre-trained model achieves an accuracy of 98.00%. |
format |
article |
author |
Md Mahibul Hasan Zhijie Wang Muhammad Ather Iqbal Hussain Kaniz Fatima |
author_facet |
Md Mahibul Hasan Zhijie Wang Muhammad Ather Iqbal Hussain Kaniz Fatima |
author_sort |
Md Mahibul Hasan |
title |
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
title_short |
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
title_full |
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
title_fullStr |
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
title_full_unstemmed |
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network |
title_sort |
bangladeshi native vehicle classification based on transfer learning with deep convolutional neural network |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doaj.org/article/ddc17f8e630043b38ea52c5be6620884 |
work_keys_str_mv |
AT mdmahibulhasan bangladeshinativevehicleclassificationbasedontransferlearningwithdeepconvolutionalneuralnetwork AT zhijiewang bangladeshinativevehicleclassificationbasedontransferlearningwithdeepconvolutionalneuralnetwork AT muhammadatheriqbalhussain bangladeshinativevehicleclassificationbasedontransferlearningwithdeepconvolutionalneuralnetwork AT kanizfatima bangladeshinativevehicleclassificationbasedontransferlearningwithdeepconvolutionalneuralnetwork |
_version_ |
1718410495443075072 |